signals-scout-data-pipelines
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: Analysis of the skill reveals no malicious patterns, obfuscation, or unauthorized exfiltration attempts. The skill is designed for monitoring internal PostHog infrastructure using provided vendor tools.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface where untrusted data from external logs or error messages (via
cdp-functions-logs-retrieveandworkflows-logs) could contain malicious instructions. It explicitly instructs the agent to treat this content strictly as data, truncate snippets, and ignore any embedded commands, which serves as a significant mitigation. - [COMMAND_EXECUTION]: The skill employs the
execute-sqltool to perform targeted, read-only queries against internal system tables (system.batch_exports,system.hog_functions,system.hog_flows). This is standard functionality for the intended purpose of gathering pipeline metadata and identifying stalled or failed processes.
Audit Metadata